How to Connect Flowise AI Agents to Live JSON Services via CData Connect AI

Flowise AI is an open-source, no-code tool for building AI workflows and custom agents visually. Its drag-and-drop interface allows you to integrate large language models (LLMs) with APIs, databases, and external systems effortlessly.

CData Connect AI enables real-time connectivity to hundreds of enterprise data sources. Through its Model Context Protocol (MCP) server, CData Connect AI bridges Flowise agents with live JSON securely and efficiently, no data replication required. By combining Flowise AI's intuitive agent builder with CData's MCP integration, users can create agents capable of fetching, analyzing, and acting upon live JSON services directly within Flowise AI workflows.

This guide shows you how to connect Flowise AI to CData Connect AI MCP, set up credentials, and enable your agents to query live JSON services in real time.

Step 1: Configure JSON Connectivity for Flowise

Connectivity to JSON from Flowise AI is made possible through CData Connect AI's Remote MCP Server. To interact with JSON services from Flowise AI, we start by creating and configuring a JSON connection in CData Connect AI.

1. Log into Connect AI, click Sources, and then click Add Connection

2. Select JSON from the Add Connection panel

3. Enter the necessary authentication properties to connect to JSON.

   See the Getting Started chapter in the data provider documentation to authenticate to your data source: The data provider models JSON APIs as bidirectional database tables and JSON files as read-only views (local files, files stored on popular cloud services, and FTP servers). The major authentication schemes are supported, including HTTP Basic, Digest, NTLM, OAuth, and FTP. See the Getting Started chapter in the data provider documentation for authentication guides.

   After setting the URI and providing any authentication values, set DataModel to more closely match the data representation to the structure of your data.

   The DataModel property is the controlling property over how your data is represented into tables and toggles the following basic configurations.

   • Document (default): Model a top-level, document view of your JSON data. The data provider returns nested elements as aggregates of data.
   • FlattenedDocuments: Implicitly join nested documents and their parents into a single table.
   • Relational: Return individual, related tables from hierarchical data. The tables contain a primary key and a foreign key that links to the parent document.

   See the Modeling JSON Data chapter for more information on configuring the relational representation. You will also find the sample data used in the following examples. The data includes entries for people, the cars they own, and various maintenance services performed on those cars.

   
4. Click Save & Test
5. Navigate to the Permissions tab and update user-based permissions

Once the connection is established, JSON data is now accessible in CData Connect AI and ready to be used with MCP enabled tools.

Add a Personal Access Token

A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from Flowise AI. It is best practice to create a separate PAT for each integration to maintain granular access control.

1. Click the gear icon () at the top right of the Connect AI app to open Settings
2. On the Settings page, go to the Access Tokens section and click Create PAT
3. Give the PAT a descriptive name and click Create

4. Copy the token when displayed and store it securely. It will not be shown again

With the JSON connection configured and a PAT generated, Flowise AI can now connect to JSON services through Connect AI.

Step 2: Configure Connect AI credentials in Flowise AI

Log in to Flowise AI workspace to set up the integration.

Add OpenAI credentials

1. Navigate to Credentials and choose Add Credential

2. Select OpenAI API from the dropdown
3. Provide a name (e.g., OpenAI_Key) and paste the API key

Add the PAT variable

1. Navigate to Variables and Add Variable

2. Set Variable Name (e.g., PAT), choose Static as type, and set the Value to Base64-encoded username:PAT
3. Click Add to save the variable

Step 3: Build the agent in Flowise AI

1. Go to Agent Flows, select Add New

2. Click the "+" icon to add a new node and choose Agent and drag the agent to the workflow

3. Connect the Start node to the Agent node

Configure agent settings

Double-click on the Agent node and fill in the details:

• Model: select ChatOpenAI or preferred model (e.g., gpt-4o-mini)
• Connect Credential: Select OpenAI API key credential which was created earlier
• Streaming: Enabled

Add the custom MCP tool

1. Under Tools, click Add Tool and choose Custom MCP
2. Fill in the JSON parameters as shown below:

 
{
  "url": "https://mcp.cloud.cdata.com/mcp",
  "headers": {
    "Authorization": "Basic {{$vars.PAT}}"
  }
}

Click the refresh icon to load available MCP actions. Once actions are listed, now Flowise agent is successfully connected to CData Connect AI MCP.

Step 4: Test and query live JSON services in Flowise

1. Open the Chat tab in Flowise
2. Type a query such as "Show top 10 records from JSON services table"
3. Observe that responses are fetched in real time via the CData Connect AI MCP connection

With the workflow run completed, Flowise demonstrates successful retrieval of Salesforce data through the CData Connect AI MCP server, with the MCP Client node providing the ability to ask questions, retrieve records, and perform actions on the data.

Get CData Connect AI

To access hundreds of SaaS, Big Data, and NoSQL sources directly from your cloud applications, try CData Connect AI today!